We investigate methods of segmenting, visualizing, and indexing presentation videos by both audio and visual data. The audio track is segmented by speaker, and augmented with key ...
We propose a new method for automated large scale gathering of Web images relevant to specified concepts. Our main goal is to build a knowledge base associated with as many conce...
In this paper, we study how a sensor-rich world can be exploited by digital recording devices such as cameras and camcorders to improve a user’s ability to search through a larg...
We present an efficient JPEG2000-based image authentication scheme, which is robust to JPEG compression and other allowed signal processing operations. Positive wavelet-based wate...
The large-scale visual concept detection and annotation task (LS-VCDT) in ImageCLEF 2009 aims at the detection of 53 concepts in consumer photos. These concepts are structured in ...